TRAILBLAZER GARAGENotes on AI, data & useful software

Ideas you can understand.
Experiments you can try.

For the people deciding what to build, and the people making it work. Practical notes, honest trade-offs and small projects from Jhony Vidal.

Find your next read
A GOOD PLACE TO STARTProduct decisions · 4 min read

Your support tool has the order, the history and the policy. Why make someone explain it all to an AI assistant again?

TAKE ONE IDEA AWAY

Give a familiar task a useful action, with a result the person can check.

Read the article
A SMALL PRODUCT DECISION 01
The app already knows.
↗Order #1042Delivery is running late✓
≡Delivery policyThe relevant information is attached✓
Less explaining. More checking.
DRAFT A REPLY

“I’ve checked your order. We’re waiting for a confirmed delivery date…”

A fictional interface sketch. The person reviews before sending.

Follow your curiosity.

Three ways into the notes.

01

Make a product decision

What should the feature do, and what should a person stay in control of?

Start with assistant memory
02

Build it. Then check it.

Find the sources, inspect the mistakes and learn whether a change helped.

Start with evaluating answers
03

Make room to learn

Choose what deserves your attention as the tools and the work change.

Try a two-week learning loop
THE NOTEBOOK

Something worth a closer look.

13 notes & counting

13 notes to explore

ON THE WORKBENCH / FLOWCHECK

A retry shouldn’t
count an order twice.

A job runs, the connection drops, and someone tries again. Does the total change? Try two fictional events and see what should happen.

Explore the project
A small interactive illustration. The Python project lets you inspect the implementation.
TWO EVENTS. ONE RETRY.No account needed
evt-1 £12.00evt-2 £10.49
Recorded events0
New events this run0
Order total£0.00

Ready. Process the two events to begin.

Jhony Vidal
THE PERSON BEHIND THE NOTES

Hello, I’m Jhony.

I’m a software engineer working with AI, data and automation. I write down the decisions, examples and mistakes that are worth returning to. The goal is to leave you with something you can understand, question or try in your own work.